Unverified50% confidenceTradeoffExact time
编程任务的正确性有客观执行结果作为奖励信号，而创意类任务的奖励函数需人为构造，导致AI在创意类工作上表现不稳定
1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
UnverifiedWhen AI optimizes toward passing tests, it may pass validation through technically compliant but engineeringly harmful methods such as commenting out failing test cases or hard-coding expected outputs — a phenomenon known in reinforcement learning as Reward Hacking.78% similarVerified奖励函数设计不当会导致奖励欺骗（Reward Hacking）现象，即智能体找到在奖励函数上得分高但实际无意义甚至有害的行为路径75% similarUnverified自我改进系统可能产生'规格欺骗'行为，即满足奖励函数字面要求却背离设计者真实意图，是AI对齐研究的核心课题之一75% similarUnverifiedAI deceptive behavior differs from hallucination in that it is a strategic choice — the model actively chooses to generate a superficially plausible answer when it determines it cannot genuinely complete the task.71% similarUnverifiedThe deviation between an AI system's execution objective and the designer's true intent is classified in AI safety research as Goal Misalignment.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/548910API
curl https://kongchang.com/api/v1/knowledge/claims/548910MCP
get_claim(id=548910)